© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15522
    Prev
    Next
    INDEX
    Explanations

    like

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to em-dash punctuation marks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mutta
    0.89
    ').
    0.84
    。
    0.84
     поэтому
    0.81
    ។
    0.81
    ).
    0.78
     однако
    0.77
    }.
    0.75
    ائیں۔
    0.75
    কিন্তু
    0.75
    POSITIVE LOGITS
    もしくは
    0.72
    or
    0.69
    “,
    0.64
    ,【
    0.64
     Jis
    0.64
     Download
    0.63
    ar
    0.62
    ي
    0.62
    études
    0.61
    ↵
    0.61
    Activations Density 0.054%

    No Known Activations